A History of Flexible Gastrointestinal Endoscopy

Deep learning-based anatomical position recognition for gastroscopic examination

BACKGROUND

The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors.

OBJECTIVE

The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination.

METHODS

A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score.

RESULTS

The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05).

CONCLUSION

The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.

How to track and register adverse events and incidents related to gastrointestinal endoscopy

Background and study aims: Gastrointestinal endoscopic procedures have evolved significantly in the last sixty years revolutionising the approach to the diagnostic and therapeutic spheres of medicine. Despite the advantages of using natural orifices to the bowel, adverse events (AE) may occur following endoscopy. Systematic AE registration is an objective in every realm of quality medicine. Despite the obvious advantage as a quality indicator, tracking endoscopy-related AE is not evident. The current study aimed at tracking all AE of all endoscopic procedures during a 3-month period. The three methods used were voluntary reporting by the endoscopist and by the patient in parallel with retrospective data analysis of patients’ electronic medical records to allow capture of all AE and comparison of the three methods. Patients and methods: During a 3-month period endoscopists and patients were requested to report any possible AE. At the end of the period, a systematic review of all patient files was performed to track all AE related to the endoscopic procedure or the endoscopyrelated anaesthesia. In total 2668 endoscopic procedures were reviewed. Results: The total AE rate was 1.95%. Only half (51.9%) of all AE were voluntarily reported by endoscopists, the other half were extracted from the electronic medical record. There were no patient-reported AE. Although the majority (66.7%) of unreported AE were mild, these findings illustrate that voluntary AE reporting is unreliable. However, the retrospective tracking process proved to be difficult and time-consuming. Conclusions: The current study highlighted that systematic registration of all endoscopy-related AE is feasible, but challenging because of multiple hurdles. More practical methods are warranted to obtain reliable and long-term data as part of endoscopy quality measures.

Endoscopic Applications of Near-Infrared Photoimmunotherapy (NIR-PIT) in Cancers of the Digestive and Respiratory Tracts

Near-infrared photoimmunotherapy (NIR-PIT) is a newly developed and promising therapy that specifically destroys target cells by irradiating antibody-photo-absorber conjugates (APCs) with NIR light. APCs bind to target molecules on the cell surface, and when exposed to NIR light, cause disruption of the cell membrane due to the ligand release reaction and dye aggregation. This leads to rapid cell swelling, blebbing, and rupture, which leads to immunogenic cell death (ICD). ICD activates host antitumor immunity, which assists in killing still viable cancer cells in the treated lesion but is also capable of producing responses in untreated lesions. In September 2020, an APC and laser system were conditionally approved for clinical use in unresectable advanced head and neck cancer in Japan, and are now routine in appropriate patients. However, most tumors have been relatively accessible in the oral cavity or neck. Endoscopes offer the opportunity to deliver light deeper within hollow organs of the body. In recent years, the application of endoscopic therapy as an alternative to surgery for the treatment of cancer has expanded, providing significant benefits to inoperable patients. In this review, we will discuss the potential applications of endoscopic NIR-PIT, especially in thoracic and gastrointestinal cancers.

Evolution and New Horizons of Endoscopy in Inflammatory Bowel Diseases

Endoscopy is the mainstay of inflammatory bowel disease (IBD) evaluation and the pillar of colorectal cancer surveillance. Endoscopic equipment, both hardware and software, are advancing at an incredible pace. Virtual chromoendoscopy is now widely available, allowing the detection of subtle inflammatory changes, thus reducing the gap between endoscopic and histologic assessment. The progress in the field of artificial intelligence (AI) has been remarkable, and numerous applications are now in an advanced stage of development. Computer-aided diagnosis (CAD) systems are likely to reshape most of the evaluations that are now prerogative of human endoscopists. Furthermore, sophisticated tools such as endocytoscopy and probe-based confocal laser endomicroscopy (pCLE) are enhancing our assessment of inflammation and dysplasia. Finally, pCLE combined with molecular labeling could pave the way to a new paradigm of personalized medicine. This review aims to summarize the main changes that occurred in the field of IBD endoscopy and to explore the most promising novelties.

Advances in gastrointestinal surgical endoscopy

Surgeons have a role in observing, detect abnormalities, disease, and other deficiencies in function which could be treated. Diagnosing and treating back days were challenging for many reasons. However, technology's innovation enhances surgeons' ability to treat their patients. The term endoscopy refers to the Greek prefix endo- ("within") and the verb skopein ("to view or observe"). Endoscopy is practical both in the diagnosis and treatment of various pathologies. Technological advances, especially in endoscopy, gradually progress and discover many possibilities which allow rapid advancement. Endoscopy development aims to assess human orifice that has not been inspected, probed, and examined over the centuries. Endoscopy over these decades is improving, which led to new problem solving using advanced technological approaches. Thus, a surgeon can solve any issues from examination, diagnosis, and treatment using progressive endoscopy evolution. This review delivers a brief history of advances in surgical endoscopy and describes current endoscopy development.